# Research Papers — 2026-01 · bundle page 158 of 189

> Full-text markdown of papers #7851–7900 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-01/page/158
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/157.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/159.md)

### FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning

Authors: Yujie Feng, Hao Wang, Jian Li, Xu Chu, Zhaolu Kang, Yiran Liu, Yasha Wang, Philip S. Yu, Xiao-Ming Wu
Published: 2026-01-07
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.03938v2

Continual learning (CL) for large language models (LLMs) aims to enable sequential knowledge acquisition without catastrophic forgetting. Memory replay methods are widely used for their practicality and effectiveness, but most rely on fixed, step-based heuristics that often misalign with the model's actual learning progress, since identical training steps can result in varying degrees of parameter change. Motivated by recent findings that LLM forgetting mirrors the Ebbinghaus human forgetting curve, we propose FOREVER (FORgEtting curVe-inspired mEmory Replay), a novel CL framework that aligns replay schedules with a model-centric notion of time. FOREVER defines model time using the magnitude of optimizer updates, allowing forgetting curve-inspired replay intervals to align with the model's internal evolution rather than raw training steps. Building on this approach, FOREVER incorporates a forgetting curve-based replay scheduler to determine when to replay and an intensity-aware regularization mechanism to adaptively control how to replay. Extensive experiments on three CL benchmarks and models ranging from 0.6B to 13B parameters demonstrate that FOREVER consistently mitigates catastrophic forgetting.

---

### Bayes-PD: Exploring a Sequence to Binding Bayesian Neural Network model trained on Phage Display data

Authors: Ilann Amiaud-Plachy, Michael Blank, Oliver Bent, Sebastien Boyer
Published: 2026-01-07
Categories: q-bio.PE, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.03930v1

Phage display is a powerful laboratory technique used to study the interactions between proteins and other molecules, whether other proteins, peptides, DNA or RNA. The under-utilisation of this data in conjunction with deep learning models for protein design may be attributed to; high experimental noise levels; the complex nature of data pre-processing; and difficulty interpreting these experimental results. In this work, we propose a novel approach utilising a Bayesian Neural Network within a training loop, in order to simulate the phage display experiment and its associated noise. Our goal is to investigate how understanding the experimental noise and model uncertainty can enable the reliable application of such models to reliably interpret phage display experiments. We validate our approach using actual binding affinity measurements instead of relying solely on proxy values derived from 'held-out' phage display rounds.

---

### FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection

Authors: Mingyu Ouyang, Kevin Qinghong Lin, Mike Zheng Shou, Hwee Tou Ng
Published: 2026-01-07
Categories: cs.CV, cs.AI, cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2601.03928v1

Vision-Language Models (VLMs) have shown remarkable performance in User Interface (UI) grounding tasks, driven by their ability to process increasingly high-resolution screenshots. However, screenshots are tokenized into thousands of visual tokens (e.g., about 4700 for 2K resolution), incurring significant computational overhead and diluting attention. In contrast, humans typically focus on regions of interest when interacting with UI. In this work, we pioneer the task of efficient UI grounding. Guided by practical analysis of the task's characteristics and challenges, we propose FocusUI, an efficient UI grounding framework that selects patches most relevant to the instruction while preserving positional continuity for precise grounding. FocusUI addresses two key challenges: (1) Eliminating redundant tokens in visual encoding. We construct patch-level supervision by fusing an instruction-conditioned score with a rule-based UI-graph score that down-weights large homogeneous regions to select distinct and instruction-relevant visual tokens. (2) Preserving positional continuity during visual token selection. We find that general visual token pruning methods suffer from severe accuracy degradation on UI grounding tasks due to broken positional information. We introduce a novel PosPad strategy, which compresses each contiguous sequence of dropped visual tokens into a single special marker placed at the sequence's last index to preserve positional continuity. Comprehensive experiments on four grounding benchmarks demonstrate that FocusUI surpasses GUI-specific baselines. On the ScreenSpot-Pro benchmark, FocusUI-7B achieves a performance improvement of 3.7% over GUI-Actor-7B. Even with only 30% visual token retention, FocusUI-7B drops by only 3.2% while achieving up to 1.44x faster inference and 17% lower peak GPU memory.

---

### A comprehensive review and analysis of different modeling approaches for financial index tracking problem

Authors: Vrinda Dhingra, Amita Sharma, Anubha Goel
Published: 2026-01-07
Categories: q-fin.PM, stat.ML
arXiv: https://arxiv.org/abs/2601.03927v1

Index tracking, also known as passive investing, has gained significant traction in financial markets due to its cost-effective and efficient approach to replicating the performance of a specific market index. This review paper provides a comprehensive overview of the various modeling approaches and strategies developed for index tracking, highlighting the strengths and limitations of each approach. We categorize the index tracking models into three broad frameworks: optimization-based models, statistical-based models and machine learning based data-driven approach. A comprehensive empirical study conducted on the S\&P 500 dataset demonstrates that the tracking error volatility model under the optimization-based framework delivers the most precise index tracking, the convex co-integration model, under the statistical-based framework achieves the strongest return-risk balance, and the deep neural network with fixed noise model within the data-driven framework provides a competitive performance with notably low turnover and high computational efficiency. By combining a critical review of the existing literature with comparative empirical analysis, this paper aims to provide insights into the evolving landscape of index tracking and its practical implications for investors and fund managers.

---

### Doc-PP: Document Policy Preservation Benchmark for Large Vision-Language Models

Authors: Haeun Jang, Hwan Chang, Hwanhee Lee
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03926v2

The deployment of Large Vision-Language Models (LVLMs) for real-world document question answering is often constrained by dynamic, user-defined policies that dictate information disclosure based on context. While ensuring adherence to these explicit constraints is critical, existing safety research primarily focuses on implicit social norms or text-only settings, overlooking the complexities of multimodal documents. In this paper, we introduce Doc-PP (Document Policy Preservation Benchmark), a novel benchmark constructed from real-world reports requiring reasoning across heterogeneous visual and textual elements under strict non-disclosure policies. Our evaluation highlights a systemic Reasoning-Induced Safety Gap: models frequently leak sensitive information when answers must be inferred through complex synthesis or aggregated across modalities, effectively circumventing existing safety constraints. Furthermore, we identify that providing extracted text improves perception but inadvertently facilitates leakage. To address these vulnerabilities, we propose DVA (Decompose-Verify-Aggregation), a structural inference framework that decouples reasoning from policy verification. Experimental results demonstrate that DVA significantly outperforms standard prompting defenses, offering a robust baseline for policy-compliant document understanding

---

### A low-complexity method for efficient depth-guided image deblurring

Authors: Ziyao Yi, Diego Valsesia, Tiziano Bianchi, Enrico Magli
Published: 2026-01-07
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2601.03924v1

Image deblurring is a challenging problem in imaging due to its highly ill-posed nature. Deep learning models have shown great success in tackling this problem but the quest for the best image quality has brought their computational complexity up, making them impractical on anything but powerful servers. Meanwhile, recent works have shown that mobile Lidars can provide complementary information in the form of depth maps that enhance deblurring quality. In this paper, we introduce a novel low-complexity neural network for depth-guided image deblurring. We show that the use of the wavelet transform to separate structural details and reduce spatial redundancy as well as efficient feature conditioning on the depth information are essential ingredients in developing a low-complexity model. Experimental results show competitive image quality against recent state-of-the-art models while reducing complexity by up to two orders of magnitude.

---

### A Gap Between Decision Trees and Neural Networks

Authors: Akash Kumar
Published: 2026-01-07
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2601.03919v2

We study when geometric simplicity of decision boundaries, used here as a notion of interpretability, can conflict with accurate approximation of axis-aligned decision trees by shallow neural networks. Decision trees induce rule-based, axis-aligned decision regions (finite unions of boxes), whereas shallow ReLU networks are typically trained as score models whose predictions are obtained by thresholding. We analyze the infinite-width, bounded-norm, single-hidden-layer ReLU class through the Radon total variation ($\mathrm{R}\mathrm{TV}$) seminorm, which controls the geometric complexity of level sets. We first show that the hard tree indicator $1_A$ has infinite $\mathrm{R}\mathrm{TV}$. Moreover, two natural split-wise continuous surrogates--piecewise-linear ramp smoothing and sigmoidal (logistic) smoothing--also have infinite $\mathrm{R}\mathrm{TV}$ in dimensions $d>1$, while Gaussian convolution yields finite $\mathrm{R}\mathrm{TV}$ but with an explicit exponential dependence on $d$. We then separate two goals that are often conflated: classification after thresholding (recovering the decision set) versus score learning (learning a calibrated score close to $1_A$). For classification, we construct a smooth barrier score $S_A$ with finite $\mathrm{R}\mathrm{TV}$ whose fixed threshold $τ=1$ exactly recovers the box. Under a mild tube-mass condition near $\partial A$, we prove an $L_1(P)$ calibration bound that decays polynomially in a sharpness parameter, along with an explicit $\mathrm{R}\mathrm{TV}$ upper bound in terms of face measures. Experiments on synthetic unions of rectangles illustrate the resulting accuracy--complexity tradeoff and how threshold selection shifts where training lands along it.

---

### Monaas: Mobile Node as a Service for TSCH-based Industrial IoT Networks

Authors: Jinting Liu, Jingwei Li, Tengfei Chang
Published: 2026-01-07
Categories: cs.NI, cs.NE
arXiv: https://arxiv.org/abs/2601.03917v1

The Time-Slotted Channel Hopping (TSCH) mode of IEEE802.15.4 standard provides ultra high end-to-end reliability and low-power consumption for application in field of Industrial Internet of Things (IIoT). With the evolving of Industrial 4.0, dynamic and bursty tasks with varied Quality of Service (QoS); effective management and utilization of growing number of mobile equipments become two major challenges for network solutions. The existing TSCH-based networks lack of a system framework design to handle these challenges. In this paper, we propose a novel, service-oriented, and hierarchical IoT network architecture named Mobile Node as a Service (Monaas). Monaas aims to systematically manage and schedule mobile nodes as on-demand, elastic resources through a new architectural design and protocol mechanisms. Its core features include a hierarchical architecture to balance global coordination with local autonomy, task-driven scheduling for proactive resource allocation, and an on-demand mobile resource integration mechanism. The feasibility and potential of the Monaas link layer mechanisms are validated through implementation and performance evaluation on an nRF52840 hardware testbed, demonstrating its potential advantages in specific scenarios. On a physical nRF52840 testbed, Monaas consistently achieved a Task Completion Rate (TCR) above 98% for high-priority tasks under bursty traffic and link degradation, whereas all representative baselines (Static TSCH, 6TiSCH Minimal, OST, FTS-SDN) remained below 40%.Moreover, its on-demand mobile resource integration activated services in 1.2 s, at least 65% faster than SDN (3.5 s) and OST/6TiSCH (> 5.8 s).

---

### HemBLIP: A Vision-Language Model for Interpretable Leukemia Cell Morphology Analysis

Authors: Julie van Logtestijn, Petru Manescu
Published: 2026-01-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.03915v1

Microscopic evaluation of white blood cell morphology is central to leukemia diagnosis, yet current deep learning models often act as black boxes, limiting clinical trust and adoption. We introduce HemBLIP, a vision language model designed to generate interpretable, morphology aware descriptions of peripheral blood cells. Using a newly constructed dataset of 14k healthy and leukemic cells paired with expert-derived attribute captions, we adapt a general-purpose VLM via both full fine-tuning and LoRA based parameter efficient training, and benchmark against the biomedical foundation model MedGEMMA. HemBLIP achieves higher caption quality and morphological accuracy, while LoRA adaptation provides further gains with significantly reduced computational cost. These results highlight the promise of vision language models for transparent and scalable hematological diagnostics.

---

### When Models Decide and When They Bind: A Two-Stage Computation for Multiple-Choice Question-Answering

Authors: Hugh Mee Wong, Rick Nouwen, Albert Gatt
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03914v1

Multiple-choice question answering (MCQA) is easy to evaluate but adds a meta-task: models must both solve the problem and output the symbol that *represents* the answer, conflating reasoning errors with symbol-binding failures. We study how language models implement MCQA internally using representational analyses (PCA, linear probes) as well as causal interventions. We find that option-boundary (newline) residual states often contain strong linearly decodable signals related to per-option correctness. Winner-identity probing reveals a two-stage progression: the winning *content position* becomes decodable immediately after the final option is processed, while the *output symbol* is represented closer to the answer emission position. Tests under symbol and content permutations support a two-stage mechanism in which models first select a winner in content space and then bind or route that winner to the appropriate symbol to emit.

---

### An Algebraic Representation Theorem for Linear GENEOs in Geometric Machine Learning

Authors: Francesco Conti, Patrizio Frosini, Nicola Quercioli
Published: 2026-01-07
Categories: math.RT, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.03910v2

Geometric and Topological Deep Learning are rapidly growing research areas that enhance machine learning through the use of geometric and topological structures. Within this framework, Group Equivariant Non-Expansive Operators (GENEOs) have emerged as a powerful class of operators for encoding symmetries and designing efficient, interpretable neural architectures. Originally introduced in Topological Data Analysis, GENEOs have since found applications in Deep Learning as tools for constructing equivariant models with reduced parameter complexity. GENEOs provide a unifying framework bridging Geometric and Topological Deep Learning and include the operator computing persistence diagrams as a special case. Their theoretical foundations rely on group actions, equivariance, and compactness properties of operator spaces, grounding them in algebra and geometry while enabling both mathematical rigor and practical relevance. While a previous representation theorem characterized linear GENEOs acting on data of the same type, many real-world applications require operators between heterogeneous data spaces. In this work, we address this limitation by introducing a new representation theorem for linear GENEOs acting between different perception pairs, based on generalized T-permutant measures. Under mild assumptions on the data domains and group actions, our result provides a complete characterization of such operators. We also prove the compactness and convexity of the space of linear GENEOs. We further demonstrate the practical impact of this theory by applying the proposed framework to improve the performance of autoencoders, highlighting the relevance of GENEOs in modern machine learning applications.

---

### Decide Then Retrieve: A Training-Free Framework with Uncertainty-Guided Triggering and Dual-Path Retrieval

Authors: Wang Chen, Guanqiang Qi, Weikang Li, Yang Li, Deguo Xia, Jizhou Huang
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03908v1

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, but existing approaches indiscriminately trigger retrieval and rely on single-path evidence construction, often introducing noise and limiting performance gains. In this work, we propose Decide Then Retrieve (DTR), a training-free framework that adaptively determines when retrieval is necessary and how external information should be selected. DTR leverages generation uncertainty to guide retrieval triggering and introduces a dual-path retrieval mechanism with adaptive information selection to better handle sparse and ambiguous queries. Extensive experiments across five open-domain QA benchmarks, multiple model scales, and different retrievers demonstrate that DTR consistently improves EM and F1 over standard RAG and strong retrieval-enhanced baselines, while reducing unnecessary retrievals. The code and data used in this paper are available at https://github.com/ChenWangHKU/DTR.

---

### Current Agents Fail to Leverage World Model as Tool for Foresight

Authors: Cheng Qian, Emre Can Acikgoz, Bingxuan Li, Xiusi Chen, Yuji Zhang, Bingxiang He, Qinyu Luo, Dilek Hakkani-Tür, Gokhan Tur, Yunzhu Li, Heng Ji
Published: 2026-01-07
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.03905v2

Agents built on vision-language models increasingly face tasks that demand anticipating future states rather than relying on short-horizon reasoning. Generative world models offer a promising remedy: agents could use them as external simulators to foresee outcomes before acting. This paper empirically examines whether current agents can leverage such world models as tools to enhance their cognition. Across diverse agentic and visual question answering tasks, we observe that some agents rarely invoke simulation (fewer than 1%), frequently misuse predicted rollouts (approximately 15%), and often exhibit inconsistent or even degraded performance (up to 5%) when simulation is available or enforced. Attribution analysis further indicates that the primary bottleneck lies in the agents' capacity to decide when to simulate, how to interpret predicted outcomes, and how to integrate foresight into downstream reasoning. These findings underscore the need for mechanisms that foster calibrated, strategic interaction with world models, paving the way toward more reliable anticipatory cognition in future agent systems.

---

### All-Quadrant Bounded Clipping GRPO: Closing the Unbounded Blind Spot for Stable and Generalizable Training

Authors: Chi Liu, Xin Chen
Published: 2026-01-07
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.03895v2

Group Relative Policy Optimization (GRPO) has emerged as a popular algorithm for reinforcement learning with large language models (LLMs). However, GRPO inherits PPO's token-level clipping while replacing token-level advantages with a single sequence-level advantage. Through a four-quadrant analysis of the (likelihood-ratio, advantage) space, we show that this combination leaves one quadrant -- negative advantage combined with an increased likelihood ratio (Q4) -- structurally unbounded, so that a few high-ratio tokens can receive very large suppressive updates that collapse entropy and narrow the reasoning boundary. To address this, we propose All-Quadrant Bounded Clipping GRPO (ABC-GRPO), which applies unconditional clipping in all four quadrants through sign-dependent boundaries. ABC-GRPO clips the likelihood ratio before multiplying by the advantage, adding a trust-region floor in Q2 and a cap in Q4 -- its negative-advantage branch coinciding with dual-clip PPO -- to yield bounded per-step policy displacement in every quadrant. On mathematical reasoning with Qwen3 base models, ABC-GRPO attains the highest Avg@64 and Pass@64: it is statistically superior to GRPO, SAPO, and dual-clip PPO and competitive with the strongest baseline (DAPO), while maintaining substantially higher entropy; the gains transfer to MATH-500 and to out-of-domain code (HumanEval). Ablations isolate Q4 as the dominant blind spot.

---

### Lightweight and perceptually-guided voice conversion for electro-laryngeal speech

Authors: Benedikt Mayrhofer, Franz Pernkopf, Philipp Aichinger, Martin Hagmüller
Published: 2026-01-07
Categories: cs.SD, cs.LG
arXiv: https://arxiv.org/abs/2601.03892v2

Electro-laryngeal (EL) speech is characterized by constant pitch, limited prosody, and mechanical noise, reducing naturalness and intelligibility. We propose a lightweight adaptation of the state-of-the-art StreamVC framework to this setting by removing pitch and energy modules and combining self-supervised pretraining with supervised fine-tuning on parallel EL and healthy (HE) speech data, guided by perceptual and intelligibility losses. Objective and subjective evaluations across different loss configurations confirm their influence: the best model variant, based on WavLM features and human-feedback predictions (+WavLM+HF), drastically reduces character error rate (CER) of EL inputs, raises naturalness mean opinion score (nMOS) from 1.1 to 3.3, and consistently narrows the gap to HE ground-truth speech in all evaluated metrics. These findings demonstrate the feasibility of adapting lightweight voice conversion architectures to EL voice rehabilitation while also identifying prosody generation and intelligibility improvements as the main remaining bottlenecks.

---

### Spectral Manifold Regularization for Stable and Modular Routing in Deep MoE Architectures

Authors: Ibrahim Delibasoglu
Published: 2026-01-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.03889v1

Mixture of Experts (MoE) architectures enable efficient scaling of neural networks but suffer from expert collapse, where routing converges to a few dominant experts. This reduces model capacity and causes catastrophic interference during adaptation. We propose the Spectrally-Regularized Mixture of Experts (SR-MoE), which imposes geometric constraints on the routing manifold to enforce structural modularity. Our method uses dual regularization: spectral norm constraints bound routing function Lipschitz continuity, while stable rank penalties preserve high-dimensional feature diversity in expert selection. We evaluate SR-MoE across architectural scales and dataset complexities using modular one-shot adaptation tasks. Results show that traditional linear gating fails with increasing depth (accuracy drops up to 4.72% due to expert entanglement), while SR-MoE maintains structural integrity (mean interference -0.32%). Our spectral constraints facilitate positive knowledge transfer, enabling localized expert updates without global performance decay. SR-MoE provides a general solution for building high-capacity, modular networks capable of stable lifelong learning.

---

### IndexTTS 2.5 Technical Report

Authors: Yunpei Li, Xun Zhou, Jinchao Wang, Lu Wang, Yong Wu, Siyi Zhou, Yiquan Zhou, Yining Wang, Yaogen Yang, Zhetao Hu, Shiyao Duan, Jiacheng Xu et al.
Published: 2026-01-07
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2601.03888v5

In prior work, we introduced IndexTTS 2, a zero-shot neural text-to-speech foundation model comprising two core components: a transformer-based Text-to-Semantic (T2S) module and a non-autoregressive Semantic-to-Mel (S2M) module, which together enable faithful emotion replication and establish the first autoregressive duration-controllable generative paradigm. Building upon this, we present IndexTTS 2.5, which significantly enhances multilingual coverage, inference speed, and overall synthesis quality through four key improvements: 1) Semantic Codec Compression: we reduce the semantic codec frame rate from 50 Hz to 25 Hz, halving sequence length and substantially lowering both training and inference costs; 2) Architectural Upgrade: we replace the U-DiT-based backbone of the S2M module with a more efficient Zipformer-based modeling architecture, achieving notable parameter reduction and faster mel-spectrogram generation; 3) Multilingual Extension: We propose three explicit cross-lingual modeling strategies, boundary-aware alignment, token-level concatenation, and instruction-guided generation, establishing practical design principles for zero-shot multilingual emotional TTS that supports Chinese, English, Japanese, and Spanish, and enables robust emotion transfer even without target-language emotional training data; 4) Reinforcement Learning Optimization: we apply GRPO in post-training of the T2S module, improving pronunciation accuracy and natrualness. Experiments show that IndexTTS 2.5 not only supports broader language coverage but also replicates emotional prosody in unseen languages under the same zero-shot setting. IndexTTS 2.5 achieves a 2.28 times improvement in RTF while maintaining comparable WER and speaker similarity to IndexTTS 2.

---

### FLNet: Flood-Induced Agriculture Damage Assessment using Super Resolution of Satellite Images

Authors: Sanidhya Ghosal, Anurag Sharma, Sushil Ghildiyal, Mukesh Saini
Published: 2026-01-07
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.03884v1

Distributing government relief efforts after a flood is challenging. In India, the crops are widely affected by floods; therefore, making rapid and accurate crop damage assessment is crucial for effective post-disaster agricultural management. Traditional manual surveys are slow and biased, while current satellite-based methods face challenges like cloud cover and low spatial resolution. Therefore, to bridge this gap, this paper introduced FLNet, a novel deep learning based architecture that used super-resolution to enhance the 10 m spatial resolution of Sentinel-2 satellite images into 3 m resolution before classifying damage. We tested our model on the Bihar Flood Impacted Croplands Dataset (BFCD-22), and the results showed an improved critical "Full Damage" F1-score from 0.83 to 0.89, nearly matching the 0.89 score of commercial high-resolution imagery. This work presented a cost-effective and scalable solution, paving the way for a nationwide shift from manual to automated, high-fidelity damage assessment.

---

### Feature-Aware One-Shot Federated Learning via Hierarchical Token Sequences

Authors: Shudong Liu, Hanwen Zhang, Xiuling Wang, Yuesheng Zhu, Guibo Luo
Published: 2026-01-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.03882v1

One-shot federated learning (OSFL) reduces the communication cost and privacy risks of iterative federated learning by constructing a global model with a single round of communication. However, most existing methods struggle to achieve robust performance on real-world domains such as medical imaging, or are inefficient when handling non-IID (Independent and Identically Distributed) data. To address these limitations, we introduce FALCON, a framework that enhances the effectiveness of OSFL over non-IID image data. The core idea of FALCON is to leverage the feature-aware hierarchical token sequences generation and knowledge distillation into OSFL. First, each client leverages a pretrained visual encoder with hierarchical scale encoding to compress images into hierarchical token sequences, which capture multi-scale semantics. Second, a multi-scale autoregressive transformer generator is used to model the distribution of these token sequences and generate the synthetic sequences. Third, clients upload the synthetic sequences along with the local classifier trained on the real token sequences to the server. Finally, the server incorporates knowledge distillation into global training to reduce reliance on precise distribution modeling. Experiments on medical and natural image datasets validate the effectiveness of FALCON in diverse non-IID scenarios, outperforming the best OSFL baselines by 9.58% in average accuracy.

---

### Women Worry, Men Adopt? Gendered Risk Perceptions and Generative AI Adoption

Authors: Fabian Stephany, Jedrzej Duszynski
Published: 2026-01-07
Categories: econ.GN, cs.AI
arXiv: https://arxiv.org/abs/2601.03880v2

Generative artificial intelligence (GenAI) is spreading rapidly across work and daily life, yet adoption remains uneven. Men use GenAI more frequently than women, potentially widening inequalities in productivity, skills, and career opportunities. Existing research has largely explained this gap through differences in access, digital skills, and confidence. We argue that these explanations are incomplete: gender differences in GenAI adoption may also reflect how women and men evaluate AI's societal risks. Using two waves (2023-2024) of the nationally representative UK Public Attitudes to Data and AI Tracker (N = 9,172), we combine descriptive analyses with gender-specific, age-stratified random forest models and a parametric score-matching analysis of repeated cross-sections. We first show that men report substantially higher levels of frequent personal GenAI use than women. We then show that this gap is especially pronounced among respondents who express concerns about AI's societal consequences, particularly its effects on mental health and the environment. Intersectional analyses show that the largest disparities arise among younger, digitally fluent individuals with high societal risk concerns, where gender gaps in personal use exceed 45 percentage points. Across predictive models, perceived societal risk has greater predictive relevance for women's adoption than for men's and ranks among the strongest predictors of women's GenAI use. Finally, in score-matched comparisons, higher optimism about AI's societal impact is associated with larger increases in women's uptake, narrowing the gender gap. We interpret these findings as an indication that unresolved AI harms may contribute to unequal access to GenAI's productivity, learning, and career benefits. The findings point to societal risk perception as an important behavioural pathway underlying digital inequality in the AI era.

---

### Staged Voxel-Level Deep Reinforcement Learning for 3D Medical Image Segmentation with Noisy Annotations

Authors: Yuyang Fu, Xiuzhen Guo, Ji Shi
Published: 2026-01-07
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2601.03875v1

Deep learning has achieved significant advancements in medical image segmentation. Currently, obtaining accurate segmentation outcomes is critically reliant on large-scale datasets with high-quality annotations. However, noisy annotations are frequently encountered owing to the complex morphological structures of organs in medical images and variations among different annotators, which can substantially limit the efficacy of segmentation models. Motivated by the fact that medical imaging annotator can correct labeling errors during segmentation based on prior knowledge, we propose an end-to-end Staged Voxel-Level Deep Reinforcement Learning (SVL-DRL) framework for robust medical image segmentation under noisy annotations. This framework employs a dynamic iterative update strategy to automatically mitigate the impact of erroneous labels without requiring manual intervention. The key advancements of SVL-DRL over existing works include: i) formulating noisy annotations as a voxel-dependent problem and addressing it through a novel staged reinforcement learning framework which guarantees robust model convergence; ii) incorporating a voxel-level asynchronous advantage actor-critic (vA3C) module that conceptualizes each voxel as an autonomous agent, which allows each agent to dynamically refine its own state representation during training, thereby directly mitigating the influence of erroneous labels; iii) designing a novel action space for the agents, along with a composite reward function that strategically combines the Dice value and a spatial continuity metric to significantly boost segmentation accuracy while maintain semantic integrity. Experiments on three public medical image datasets demonstrates State-of-The-Art (SoTA) performance under various experimental settings, with an average improvement of over 3\% in both Dice and IoU scores.

---

### Evaluating Small Decoder-Only Language Models for Grammar Correction and Text Simplification

Authors: Anthony Lamelas
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03874v1

Large language models have become extremely popular recently due to their ability to achieve strong performance on a variety of tasks, such as text generation and rewriting, but their size and computation cost make them difficult to access, deploy, and secure in many settings. This paper investigates whether small, decoder-only language models can provide an efficient alternative for the tasks of grammar correction and text simplification. The experiments in this paper focus on testing small language models out of the box, fine-tuned, and run sequentially on the JFLEG and ASSET datasets using established metrics. The results show that while SLMs may learn certain behaviors well, their performance remains below strong baselines and current LLMs. The results also show that SLMs struggle with retaining meaning and hallucinations. These findings suggest that despite their efficiency advantages, current SLMs are not yet competitive enough with modern LLMs for rewriting, and further advances in training are required for SLMs to close the performance gap between them and today's LLMs.

---

### Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning

Authors: Jinyang Wu, Guocheng Zhai, Ruihan Jin, Jiahao Yuan, Yuhao Shen, Shuai Zhang, Zhengqi Wen, Jianhua Tao
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03872v2

The integration of large language models (LLMs) with external tools has significantly expanded the capabilities of AI agents. However, as the diversity of both LLMs and tools increases, selecting the optimal model-tool combination becomes a high-dimensional optimization challenge. Existing approaches often rely on a single model or fixed tool-calling logic, failing to exploit the performance variations across heterogeneous model-tool pairs. In this paper, we present ATLAS (Adaptive Tool-LLM Alignment and Synergistic Invocation), a dual-path framework for dynamic tool usage in cross-domain complex reasoning. ATLAS operates via a dual-path approach: (1) \textbf{training-free cluster-based routing} that exploits empirical priors for domain-specific alignment, and (2) \textbf{RL-based multi-step routing} that explores autonomous trajectories for out-of-distribution generalization. Extensive experiments across 15 benchmarks demonstrate that our method outperforms closed-source models like GPT-4o, surpassing existing routing methods on both in-distribution (+10.1%) and out-of-distribution (+13.1%) tasks. Furthermore, our framework shows significant gains in visual reasoning by orchestrating specialized multi-modal tools.

---

### Bayesian Monocular Depth Refinement via Neural Radiance Fields

Authors: Arun Muthukkumar
Published: 2026-01-07
Categories: cs.CV, cs.GR, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2601.03869v2

Monocular depth estimation has applications in many fields, such as autonomous navigation and extended reality, making it an essential computer vision task. However, current methods often produce smooth depth maps that lack the fine geometric detail needed for accurate scene understanding. We propose MDENeRF, an iterative framework that refines monocular depth estimates using depth information from Neural Radiance Fields (NeRFs). MDENeRF consists of three components: (1) an initial monocular estimate for global structure, (2) a NeRF trained on perturbed viewpoints, with per-pixel uncertainty, and (3) Bayesian fusion of the noisy monocular and NeRF depths. We derive NeRF uncertainty from the volume rendering process to iteratively inject high-frequency fine details. Meanwhile, our monocular prior maintains global structure. We demonstrate improvements on key metrics and experiments using indoor scenes from the SUN RGB-D dataset.

---

### What Matters For Safety Alignment?

Authors: Xing Li, Hui-Ling Zhen, Lihao Yin, Xianzhi Yu, Zhenhua Dong, Mingxuan Yuan
Published: 2026-01-07
Categories: cs.CL, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2601.03868v2

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We systematically investigate and compare the influence of six critical intrinsic model characteristics and three external attack techniques. Our large-scale evaluation is conducted using 32 recent, popular LLMs and LRMs across thirteen distinct model families, spanning a parameter scale from 3B to 235B. The assessment leverages five established safety datasets and probes model vulnerabilities with 56 jailbreak techniques and four CoT attack strategies, resulting in 4.6M API calls. Our key empirical findings are fourfold. First, we identify the LRMs GPT-OSS-20B, Qwen3-Next-80B-A3B-Thinking, and GPT-OSS-120B as the top-three safest models, which substantiates the significant advantage of integrated reasoning and self-reflection mechanisms for robust safety alignment. Second, post-training and knowledge distillation may lead to a systematic degradation of safety alignment. We thus argue that safety must be treated as an explicit constraint or a core optimization objective during these stages, not merely subordinated to the pursuit of general capability. Third, we reveal a pronounced vulnerability: employing a CoT attack via a response prefix can elevate the attack success rate by 3.34x on average and from 0.6% to 96.3% for Seed-OSS-36B-Instruct. This critical finding underscores the safety risks inherent in text-completion interfaces and features that allow user-defined response prefixes in LLM services, highlighting an urgent need for architectural and deployment safeguards. Fourth, roleplay, prompt injection, and gradient-based search for adversarial prompts are the predominant methodologies for eliciting unaligned behaviors in modern models.

---

### PartisanLens: A Multilingual Dataset of Hyperpartisan and Conspiratorial Immigration Narratives in European Media

Authors: Michele Joshua Maggini, Paloma Piot, Anxo Pérez, Erik Bran Marino, Lúa Santamaría Montesinos, Ana Lisboa, Marta Vázquez Abuín, Javier Parapar, Pablo Gamallo
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03860v1

Detecting hyperpartisan narratives and Population Replacement Conspiracy Theories (PRCT) is essential to addressing the spread of misinformation. These complex narratives pose a significant threat, as hyperpartisanship drives political polarisation and institutional distrust, while PRCTs directly motivate real-world extremist violence, making their identification critical for social cohesion and public safety. However, existing resources are scarce, predominantly English-centric, and often analyse hyperpartisanship, stance, and rhetorical bias in isolation rather than as interrelated aspects of political discourse. To bridge this gap, we introduce \textsc{PartisanLens}, the first multilingual dataset of \num{1617} hyperpartisan news headlines in Spanish, Italian, and Portuguese, annotated in multiple political discourse aspects. We first evaluate the classification performance of widely used Large Language Models (LLMs) on this dataset, establishing robust baselines for the classification of hyperpartisan and PRCT narratives. In addition, we assess the viability of using LLMs as automatic annotators for this task, analysing their ability to approximate human annotation. Results highlight both their potential and current limitations. Next, moving beyond standard judgments, we explore whether LLMs can emulate human annotation patterns by conditioning them on socio-economic and ideological profiles that simulate annotator perspectives. At last, we provide our resources and evaluation, \textsc{PartisanLens} supports future research on detecting partisan and conspiratorial narratives in European contexts.

---

### What Does Loss Optimization Actually Teach, If Anything? Knowledge Dynamics in Continual Pre-training of LLMs

Authors: Seyed Mahed Mousavi, Simone Alghisi, Giuseppe Riccardi
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03858v1

Continual Pre-Training (CPT) is widely used for acquiring and updating factual knowledge in LLMs. This practice treats loss as a proxy for knowledge learning, while offering no grounding into how it changes during training. We study CPT as a knowledge learning process rather than a solely optimization problem. We construct a controlled, distribution-matched benchmark of factual documents and interleave diagnostic probes directly into the CPT loop, enabling epoch-level measurement of knowledge acquisition dynamics and changes in Out-Of-Domain (OOD) general skills (e.g., math). We further analyze how CPT reshapes knowledge circuits during training. Across three instruction-tuned LLMs and multiple CPT strategies, optimization and learning systematically diverge as loss decreases monotonically while factual learning is unstable and non-monotonic. Acquired facts are rarely consolidated, learning is strongly conditioned on prior exposure, and OOD performance degrades from early epochs. Circuit analysis reveals rapid reconfiguration of knowledge pathways across epochs, providing an explanation for narrow acquisition windows and systematic forgetting. These results show that loss optimization is misaligned with learning progress in CPT and motivate evaluation of stopping criteria based on task-level learning dynamics.

---

### From No-Regret to Strategically Robust Learning in Repeated Auctions

Authors: Junyao Zhao
Published: 2026-01-07
Categories: cs.GT, cs.LG, econ.TH
arXiv: https://arxiv.org/abs/2601.03853v2

In Bayesian single-item auctions, a monotone bidding strategy--one that prescribes a higher bid for a higher value type--can be equivalently represented as a partition of the quantile space into consecutive intervals corresponding to increasing bids. Kumar et al. (2024) prove that agile online gradient descent (OGD), when used to update a monotone bidding strategy through its quantile representation, is strategically robust in repeated first-price auctions: when all bidders employ agile OGD in this way, the auctioneer's average revenue per round is at most the revenue of Myerson's optimal auction, regardless of how she adjusts the reserve price over time. In this work, we show that this strategic robustness guarantee is not unique to agile OGD or to the first-price auction: any no-regret learning algorithm, when fed gradient feedback with respect to the quantile representation, is strategically robust, even if the auction format changes every round, provided the format satisfies allocation monotonicity and voluntary participation. In particular, the multiplicative weights update (MWU) algorithm simultaneously achieves the optimal regret guarantee and a strong strategic robustness guarantee in this auction setting. At a technical level, our results are established via a simple relation that bridges Myerson's auction theory and standard no-regret learning theory.

---

### Rethinking Table Pruning in TableQA: From Sequential Revisions to Gold Trajectory-Supervised Parallel Search

Authors: Yu Guo, Shenghao Ye, Shuangwu Chen, Zijian Wen, Tao Zhang, Qirui Bai, Dong Jin, Yunpeng Hou, Huasen He, Jian Yang, Xiaobin Tan
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03851v2

Table Question Answering (TableQA) benefits significantly from table pruning, which extracts compact sub-tables by eliminating redundant cells to streamline downstream reasoning. However, existing pruning methods typically rely on sequential revisions driven by unreliable critique signals, often failing to detect the loss of answer-critical data. To address this limitation, we propose TabTrim, a novel table pruning framework which transforms table pruning from sequential revisions to gold trajectory-supervised parallel search. TabTrim derives a gold pruning trajectory using the intermediate sub-tables in the execution process of gold SQL queries, and trains a pruner and a verifier to make the step-wise pruning result align with the gold pruning trajectory. During inference, TabTrim performs parallel search to explore multiple candidate pruning trajectories and identify the optimal sub-table. Extensive experiments demonstrate that TabTrim achieves state-of-the-art performance across diverse tabular reasoning tasks: TabTrim-8B reaches 73.5% average accuracy, outperforming the strongest baseline by 3.2%, including 79.4% on WikiTQ and 61.2% on TableBench.

---

### Investigating the Grounding Bottleneck for a Large-Scale Configuration Problem: Existing Tools and Constraint-Aware Guessing

Authors: Veronika Semmelrock, Gerhard Friedrich
Published: 2026-01-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.03850v1

Answer set programming (ASP) aims to realize the AI vision: The user specifies the problem, and the computer solves it. Indeed, ASP has made this vision true in many application domains. However, will current ASP solving techniques scale up for large configuration problems? As a benchmark for such problems, we investigated the configuration of electronic systems, which may comprise more than 30,000 components. We show the potential and limits of current ASP technology, focusing on methods that address the so-called grounding bottleneck, i.e., the sharp increase of memory demands in the size of the problem instances. To push the limits, we investigated the incremental solving approach, which proved effective in practice. However, even in the incremental approach, memory demands impose significant limits. Based on an analysis of grounding, we developed the method constraint-aware guessing, which significantly reduced the memory need.

---

### Implementing the First-Order Logic of Here and There

Authors: Jens Otten, Torsten Schaub
Published: 2026-01-07
Categories: cs.LO, cs.AI, cs.PL
arXiv: https://arxiv.org/abs/2601.03848v1

We present automated theorem provers for the first-order logic of here and there (HT). They are based on a native sequent calculus for the logic of HT and an axiomatic embedding of the logic of HT into intuitionistic logic. The analytic proof search in the sequent calculus is optimized by using free variables and skolemization. The embedding is used in combination with sequent, tableau and connection calculi for intuitionistic first-order logic. All provers are evaluated on a large benchmark set of first-order formulas, providing a foundation for the development of more efficient HT provers.

---

### xDNN(ASP): Explanation Generation System for Deep Neural Networks powered by Answer Set Programming

Authors: Ly Ly Trieu, Tran Cao Son
Published: 2026-01-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.03847v1

Explainable artificial intelligence (xAI) has gained significant attention in recent years. Among other things, explainablility for deep neural networks has been a topic of intensive research due to the meteoric rise in prominence of deep neural networks and their "black-box" nature. xAI approaches can be characterized along different dimensions such as their scope (global versus local explanations) or underlying methodologies (statistic-based versus rule-based strategies). Methods generating global explanations aim to provide reasoning process applicable to all possible output classes while local explanation methods focus only on a single, specific class. SHAP (SHapley Additive exPlanations), a well-known statistical technique, identifies important features of a network. Deep neural network rule extraction method constructs IF-THEN rules that link input conditions to a class. Another approach focuses on generating counterfactuals which help explain how small changes to an input can affect the model's predictions. However, these techniques primarily focus on the input-output relationship and thus neglect the structure of the network in explanation generation. In this work, we propose xDNN(ASP), an explanation generation system for deep neural networks that provides global explanations. Given a neural network model and its training data, xDNN(ASP) extracts a logic program under answer set semantics that-in the ideal case-represents the trained model, i.e., answer sets of the extracted program correspond one-to-one to input-output pairs of the network. We demonstrate experimentally, using two synthetic datasets, that not only the extracted logic program maintains a high-level of accuracy in the prediction task, but it also provides valuable information for the understanding of the model such as the importance of features as well as the impact of hidden nodes on the prediction. The latter can be used as a guide for reducing the number of nodes used in hidden layers, i…

---

### When Numbers Start Talking: Implicit Numerical Coordination Among LLM-Based Agents

Authors: Alessio Buscemi, Daniele Proverbio, Alessandro Di Stefano, The-Anh Han, German Castignani, Pietro Liò
Published: 2026-01-07
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2601.03846v2

LLMs-based agents increasingly operate in multi-agent environments where strategic interaction and coordination are required. While existing work has largely focused on individual agents or on interacting agents sharing explicit communication, less is known about how interacting agents coordinate implicitly. In particular, agents may engage in covert communication, relying on indirect or non-linguistic signals embedded in their actions rather than on explicit messages. This paper presents a game-theoretic study of covert communication in LLM-driven multi-agent systems. We analyse interactions across four canonical game-theoretic settings under different communication regimes, including explicit, restricted, and absent communication. Considering heterogeneous agent personalities and both one-shot and repeated games, we characterise when covert signals emerge and how they shape coordination and strategic outcomes.

---

### Formally Explaining Decision Tree Models with Answer Set Programming

Authors: Akihiro Takemura, Masayuki Otani, Katsumi Inoue
Published: 2026-01-07
Categories: cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2601.03845v1

Decision tree models, including random forests and gradient-boosted decision trees, are widely used in machine learning due to their high predictive performance. However, their complex structures often make them difficult to interpret, especially in safety-critical applications where model decisions require formal justification. Recent work has demonstrated that logical and abductive explanations can be derived through automated reasoning techniques. In this paper, we propose a method for generating various types of explanations, namely, sufficient, contrastive, majority, and tree-specific explanations, using Answer Set Programming (ASP). Compared to SAT-based approaches, our ASP-based method offers greater flexibility in encoding user preferences and supports enumeration of all possible explanations. We empirically evaluate the approach on a diverse set of datasets and demonstrate its effectiveness and limitations compared to existing methods.

---

### XAI-LAW: A Logic Programming Tool for Modeling, Explaining, and Learning Legal Decisions

Authors: Agostino Dovier, Talissa Dreossi, Andrea Formisano, Benedetta Strizzolo
Published: 2026-01-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.03844v1

We propose an approach to model articles of the Italian Criminal Code (ICC), using Answer Set Programming (ASP), and to semi-automatically learn legal rules from examples based on prior judicial decisions. The developed tool is intended to support legal experts during the criminal trial phase by providing reasoning and possible legal outcomes. The methodology involves analyzing and encoding articles of the ICC in ASP, including "crimes against the person" and property offenses. The resulting model is validated on a set of previous verdicts and refined as necessary. During the encoding process, contradictions may arise; these are properly handled by the system, which also generates possible decisions for new cases and provides explanations through a tool that leverages the "supportedness" of stable models. The automatic explainability offered by the tool can also be used to clarify the logic behind judicial decisions, making the decision-making process more interpretable. Furthermore, the tool integrates an inductive logic programming system for ASP, which is employed to generalize legal rules from case examples.

---

### On the Trap Space Semantics of Normal Logic Programs

Authors: Van-Giang Trinh, Sylvain Soliman, François Fages, Belaid Benhamou
Published: 2026-01-07
Categories: cs.LO, cs.AI
arXiv: https://arxiv.org/abs/2601.03842v1

The logical semantics of normal logic programs has traditionally been based on the notions of Clark's completion and two-valued or three-valued canonical models, including supported, stable, regular, and well-founded models. Two-valued interpretations can also be seen as states evolving under a program's update operator, producing a transition graph whose fixed points and cycles capture stable and oscillatory behaviors, respectively. We refer to this view as dynamical semantics since it characterizes the program's meaning in terms of state-space trajectories, as first introduced in the stable (supported) class semantics. Recently, we have established a formal connection between Datalog^\neg programs (i.e., normal logic programs without function symbols) and Boolean networks, leading to the introduction of the trap space concept for Datalog^\neg programs. In this paper, we generalize the trap space concept to arbitrary normal logic programs, introducing trap space semantics as a new approach to their interpretation. This new semantics admits both model-theoretic and dynamical characterizations, providing a comprehensive approach to understanding program behavior. We establish the foundational properties of the trap space semantics and systematically relate it to the established model-theoretic semantics, including the stable (supported), stable (supported) partial, regular, and L-stable model semantics, as well as to the dynamical stable (supported) class semantics. Our results demonstrate that the trap space semantics offers a unified and precise framework for proving the existence of supported classes, strict stable (supported) classes, and regular models, in addition to uncovering and formalizing deeper relationships among the existing semantics of normal logic programs.

---

### Defeasible Conditionals using Answer Set Programming

Authors: Racquel Dennison, Jesse Heyninck, Thomas Meyer
Published: 2026-01-07
Categories: cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2601.03840v1

Defeasible entailment is concerned with drawing plausible conclusions from incomplete information. A foundational framework for modelling defeasible entailment is the KLM framework. Introduced by Kraus, Lehmann, and Magidor, the KLM framework outlines several key properties for defeasible entailment. One of the most prominent algorithms within this framework is Rational Closure (RC). This paper presents a declarative definition for computing RC using Answer Set Programming (ASP). Our approach enables the automatic construction of the minimal ranked model from a given knowledge base and supports entailment checking for specified queries. We formally prove the correctness of our ASP encoding and conduct empirical evaluations to compare the performance of our implementation with that of existing imperative implementations, specifically the InfOCF solver. The results demonstrate that our ASP-based approach adheres to RC's theoretical foundations and offers improved computational efficiency.

---

### Logic Tensor Network-Enhanced Generative Adversarial Network

Authors: Nijesh Upreti, Vaishak Belle
Published: 2026-01-07
Categories: cs.LG, cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2601.03839v1

In this paper, we introduce Logic Tensor Network-Enhanced Generative Adversarial Network (LTN-GAN), a novel framework that enhances Generative Adversarial Networks (GANs) by incorporating Logic Tensor Networks (LTNs) to enforce domain-specific logical constraints during the sample generation process. Although GANs have shown remarkable success in generating realistic data, they often lack mechanisms to incorporate prior knowledge or enforce logical consistency, limiting their applicability in domains requiring rule adherence. LTNs provide a principled way to integrate first-order logic with neural networks, enabling models to reason over and satisfy logical constraints. By combining the strengths of GANs for realistic data synthesis with LTNs for logical reasoning, we gain valuable insights into how logical constraints influence the generative process while improving both the diversity and logical consistency of the generated samples. We evaluate LTN-GAN across multiple datasets, including synthetic datasets (gaussian, grid, rings) and the MNIST dataset, demonstrating that our model significantly outperforms traditional GANs in terms of adherence to predefined logical constraints while maintaining the quality and diversity of generated samples. This work highlights the potential of neuro-symbolic approaches to enhance generative modeling in knowledge-intensive domains.

---

### Beyond Physical Labels: Redefining Domains for Robust WiFi-based Gesture Recognition

Authors: Xiang Zhang, Huan Yan, Jinyang Huang, Bin Liu, Yuanhao Feng, Jianchun Liu, Meng Li, Fusang Zhang, Zhi Liu
Published: 2026-01-07
Categories: cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2601.03825v2

In this paper, we propose GesFi, a novel WiFi-based gesture recognition system that introduces WiFi latent domain mining to redefine domains directly from the data itself. GesFi first processes raw sensing data collected from WiFi receivers using CSI-ratio denoising, Short-Time Fast Fourier Transform, and visualization techniques to generate standardized input representations. It then employs class-wise adversarial learning to suppress gesture semantic and leverages unsupervised clustering to automatically uncover latent domain factors responsible for distributional shifts. These latent domains are then aligned through adversarial learning to support robust cross-domain generalization. Finally, the system is applied to the target environment for robust gesture inference. We deployed GesFi under both single-pair and multi-pair settings using commodity WiFi transceivers, and evaluated it across multiple public datasets and real-world environments. Compared to state-of-the-art baselines, GesFi achieves up to 78% and 50% performance improvements over existing adversarial methods, and consistently outperforms prior generalization approaches across most cross-domain tasks.

---

### IDESplat: Iterative Depth Probability Estimation for Generalizable 3D Gaussian Splatting

Authors: Wei Long, Haifeng Wu, Shiyin Jiang, Jinhua Zhang, Xinchun Ji, Shuhang Gu
Published: 2026-01-07
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.03824v3

Generalizable 3D Gaussian Splatting aims to directly predict Gaussian parameters using a feed-forward network for scene reconstruction. Among these parameters, Gaussian means are particularly difficult to predict, so depth is usually estimated first and then unprojected to obtain the Gaussian sphere centers. Existing methods typically rely solely on a single warp to estimate depth probability, which hinders their ability to fully leverage cross-view geometric cues, resulting in unstable and coarse depth maps. To address this limitation, we propose IDESplat, which iteratively applies warp operations to boost depth probability estimation for accurate Gaussian mean prediction. First, to eliminate the inherent instability of a single warp, we introduce a Depth Probability Boosting Unit (DPBU) that integrates epipolar attention maps produced by cascading warp operations in a multiplicative manner. Next, we construct an iterative depth estimation process by stacking multiple DPBUs, progressively identifying potential depth candidates with high likelihood. As IDESplat iteratively boosts depth probability estimates and updates the depth candidates, the depth map is gradually refined, resulting in accurate Gaussian means. We conduct experiments on RealEstate10K, ACID, and DL3DV. IDESplat achieves outstanding reconstruction quality and state-of-the-art performance with real-time efficiency. On RE10K, it outperforms DepthSplat by 0.33 dB in PSNR, using only 10.7% of the parameters and 70% of the memory. Additionally, our IDESplat improves PSNR by 2.95 dB over DepthSplat on the DTU dataset in cross-dataset experiments, demonstrating its strong generalization ability.

---

### Step Potential Advantage Estimation: Harnessing Intermediate Confidence and Correctness for Efficient Mathematical Reasoning

Authors: Fei Wu, Zhenrong Zhang, Qikai Chang, Jianshu Zhang, Quan Liu, Jun Du
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03823v1

Reinforcement Learning with Verifiable Rewards (RLVR) elicits long chain-of-thought reasoning in large language models (LLMs), but outcome-based rewards lead to coarse-grained advantage estimation. While existing approaches improve RLVR via token-level entropy or sequence-level length control, they lack a semantically grounded, step-level measure of reasoning progress. As a result, LLMs fail to distinguish necessary deduction from redundant verification: they may continue checking after reaching a correct solution and, in extreme cases, overturn a correct trajectory into an incorrect final answer. To remedy the lack of process supervision, we introduce a training-free probing mechanism that extracts intermediate confidence and correctness and combines them into a Step Potential signal that explicitly estimates the reasoning state at each step. Building on this signal, we propose Step Potential Advantage Estimation (SPAE), a fine-grained credit assignment method that amplifies potential gains, penalizes potential drops, and applies penalty after potential saturates to encourage timely termination. Experiments across multiple benchmarks show SPAE consistently improves accuracy while substantially reducing response length, outperforming strong RL baselines and recent efficient reasoning and token-level advantage estimation methods. The code is available at https://github.com/cii030/SPAE-RL.

---

### ROI-Reasoning: Rational Optimization for Inference via Pre-Computation Meta-Cognition

Authors: Muyang Zhao, Chunhao Tian, Qi Qi, Hao Sun
Published: 2026-01-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.03822v2

Large language models (LLMs) can achieve strong reasoning performance with sufficient computation, but they do not inherently know how much computation a task requires. We study budgeted inference-time reasoning for multiple problems under a strict global token constraint and formulate it as an Ordered Stochastic Multiple-Choice Knapsack Problem (OS-MCKP). This perspective highlights a meta-cognitive requirement---anticipating problem difficulty and allocating computation strategically. We propose ROI-Reasoning, a two-stage framework that endows LLMs with intrinsic, budget-aware rationality. First, Meta-Cognitive Fine-Tuning teaches models to predict reasoning cost levels and decide whether a problem is worth attempting before generation. Next, Rationality-Aware Reinforcement Learning optimizes sequential decision making under a hard token budget, allowing models to learn long-horizon allocation strategies. Experiments across mathematical reasoning, multiple-choice question answering, and code generation show that ROI-Reasoning improves scores and generally reduces reference-order regret under tight budgets, with up to a \textbf{417\%} relative score improvement over the strongest same-backbone baseline in mathematics.

---

### AI Generated Text Detection

Authors: Adilkhan Alikhanov, Aidar Amangeldi, Diar Demeubay, Dilnaz Akhmetzhan, Nurbek Moldakhmetov, Omar Polat, Galymzhan Zharas
Published: 2026-01-07
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.03812v1

The rapid development of large language models has led to an increase in AI-generated text, with students increasingly using LLM-generated content as their own work, which violates academic integrity. This paper presents an evaluation of AI text detection methods, including both traditional machine learning models and transformer-based architectures. We utilize two datasets, HC3 and DAIGT v2, to build a unified benchmark and apply a topic-based data split to prevent information leakage. This approach ensures robust generalization across unseen domains. Our experiments show that TF-IDF logistic regression achieves a reasonable baseline accuracy of 82.87%. However, deep learning models outperform it. The BiLSTM classifier achieves an accuracy of 88.86%, while DistilBERT achieves a similar accuracy of 88.11% with the highest ROC-AUC score of 0.96, demonstrating the strongest overall performance. The results indicate that contextual semantic modeling is significantly superior to lexical features and highlight the importance of mitigating topic memorization through appropriate evaluation protocols. The limitations of this work are primarily related to dataset diversity and computational constraints. In future work, we plan to expand dataset diversity and utilize parameter-efficient fine-tuning methods such as LoRA. We also plan to explore smaller or distilled models and employ more efficient batching strategies and hardware-aware optimization.

---

### EvalBlocks: A Modular Pipeline for Rapidly Evaluating Foundation Models in Medical Imaging

Authors: Jan Tagscherer, Sarah de Boer, Lena Philipp, Fennie van der Graaf, Dré Peeters, Joeran Bosma, Lars Leijten, Bogdan Obreja, Ewoud Smit, Alessa Hering
Published: 2026-01-07
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.03811v2

Developing foundation models in medical imaging requires continuous monitoring of downstream performance. Researchers are burdened with tracking numerous experiments, design choices, and their effects on performance, often relying on ad-hoc, manual workflows that are inherently slow and error-prone. We introduce EvalBlocks, a modular, plug-and-play framework for efficient evaluation of foundation models during development. Built on Snakemake, EvalBlocks supports seamless integration of new datasets, foundation models, aggregation methods, and evaluation strategies. All experiments and results are tracked centrally and are reproducible with a single command, while efficient caching and parallel execution enable scalable use on shared compute infrastructure. Demonstrated on five state-of-the-art foundation models and three medical imaging classification tasks, EvalBlocks streamlines model evaluation, enabling researchers to iterate faster and focus on model innovation rather than evaluation logistics. The framework is released as open source software at https://github.com/DIAGNijmegen/eval-blocks.

---

### From Brute Force to Semantic Insight: Performance-Guided Data Transformation Design with LLMs

Authors: Usha Shrestha, Dmitry Ignatov, Radu Timofte
Published: 2026-01-07
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.03808v2

Large language models (LLMs) have achieved notable performance in code synthesis; however, data-aware augmentation remains a limiting factor, handled via heuristic design or brute-force approaches. We introduce a performance-aware, closed-loop solution in the NNGPT ecosystem of projects that enables LLMs to autonomously engineer optimal transformations by internalizing empirical performance cues. We fine-tune LLMs with Low-Rank Adaptation on a novel repository of more than 6,000 empirically evaluated PyTorch augmentation functions, each annotated solely by downstream model accuracy. Training uses pairwise performance ordering (better-worse transformations), enabling alignment through empirical feedback without reinforcement learning, reward models, or symbolic objectives. This reduces the need for exhaustive search, achieving up to 600x times fewer evaluated candidates than brute-force discovery while maintaining competitive peak accuracy and shifting generation from random synthesis to task-aligned design. Ablation studies show that structured Chain-of-Thought prompting introduces syntactic noise and degrades performance, whereas direct prompting ensures stable optimization in performance-critical code tasks. Qualitative and quantitative analyses demonstrate that the model internalizes semantic performance cues rather than memorizing syntax. These results show that LLMs can exhibit task-level reasoning through non-textual feedback loops, bypassing explicit symbolic rewards.

---

### Detecting Semantic Backdoors in a Mystery Shopping Scenario

Authors: Arpad Berta, Gabor Danner, Istvan Hegedus, Mark Jelasity
Published: 2026-01-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.03805v1

Detecting semantic backdoors in classification models--where some classes can be activated by certain natural, but out-of-distribution inputs--is an important problem that has received relatively little attention. Semantic backdoors are significantly harder to detect than backdoors that are based on trigger patterns due to the lack of such clearly identifiable patterns. We tackle this problem under the assumption that the clean training dataset and the training recipe of the model are both known. These assumptions are motivated by a consumer protection scenario, in which the responsible authority performs mystery shopping to test a machine learning service provider. In this scenario, the authority uses the provider's resources and tools to train a model on a given dataset and tests whether the provider included a backdoor. In our proposed approach, the authority creates a reference model pool by training a small number of clean and poisoned models using trusted infrastructure, and calibrates a model distance threshold to identify clean models. We propose and experimentally analyze a number of approaches to compute model distances and we also test a scenario where the provider performs an adaptive attack to avoid detection. The most reliable method is based on requesting adversarial training from the provider. The model distance is best measured using a set of input samples generated by inverting the models in such a way as to maximize the distance from clean samples. With these settings, our method can often completely separate clean and poisoned models, and it proves to be superior to state-of-the-art backdoor detectors as well.

---

### Quantum vs. Classical Machine Learning: A Benchmark Study for Financial Prediction

Authors: Rehan Ahmad, Muhammad Kashif, Nouhaila Innan, Muhammad Shafique
Published: 2026-01-07
Categories: cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2601.03802v1

In this paper, we present a reproducible benchmarking framework that systematically compares QML models with architecture-matched classical counterparts across three financial tasks: (i) directional return prediction on U.S. and Turkish equities, (ii) live-trading simulation with Quantum LSTMs versus classical LSTMs on the S\&P 500, and (iii) realized volatility forecasting using Quantum Support Vector Regression. By standardizing data splits, features, and evaluation metrics, our study provides a fair assessment of when current-generation QML models can match or exceed classical methods. Our results reveal that quantum approaches show performance gains when data structure and circuit design are well aligned. In directional classification, hybrid quantum neural networks surpass the parameter-matched ANN by \textbf{+3.8 AUC} and \textbf{+3.4 accuracy points} on \texttt{AAPL} stock and by \textbf{+4.9 AUC} and \textbf{+3.6 accuracy points} on Turkish stock \texttt{KCHOL}. In live trading, the QLSTM achieves higher risk-adjusted returns in \textbf{two of four} S\&P~500 regimes. For volatility forecasting, an angle-encoded QSVR attains the \textbf{lowest QLIKE} on \texttt{KCHOL} and remains within $\sim$0.02-0.04 QLIKE of the best classical kernels on \texttt{S\&P~500} and \texttt{AAPL}. Our benchmarking framework clearly identifies the scenarios where current QML architectures offer tangible improvements and where established classical methods continue to dominate.

---

### Physically Consistent Machine Learning for Melting Temperature Prediction of Refractory High-Entropy Alloys

Authors: Mohd Hasnain
Published: 2026-01-07
Categories: cond-mat.mtrl-sci, cs.LG
arXiv: https://arxiv.org/abs/2601.03801v1

Predicting the melting temperature (Tm) of multi-component and high-entropy alloys (HEAs) is critical for high-temperature applications but computationally expensive using traditional CALPHAD or DFT methods. In this work, we develop a gradient-boosted decision tree (XGBoost) model to predict Tm for complex alloys based on elemental properties. To ensure physical consistency, we address the issue of data leakage by excluding temperature-dependent thermodynamic descriptors (such as Gibbs free energy of mixing) and instead rely on physically motivated elemental features. The optimized model achieves a coefficient of determination (R2) of 0.948 and a Mean Squared Error (MSE) of 9928 which is about 5% relative error for HEAs on a validation set of approximately 1300 compositions. Crucially, we validate the model using the Valence Electron Concentration (VEC) rule. Without explicit constraints during training, the model successfully captures the known stability transition between BCC and FCC phases at a VEC of approximately 6.87. These results demonstrate that data-driven models, when properly feature-engineered, can capture fundamental metallurgical principles for rapid alloy screening.

---

### Where meaning lives: Layer-wise accessibility of psycholinguistic features in encoder and decoder language models

Authors: Taisiia Tikhomirova, Dirk U. Wulff
Published: 2026-01-07
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.03798v1

Understanding where transformer language models encode psychologically meaningful aspects of meaning is essential for both theory and practice. We conduct a systematic layer-wise probing study of 58 psycholinguistic features across 10 transformer models, spanning encoder-only and decoder-only architectures, and compare three embedding extraction methods. We find that apparent localization of meaning is strongly method-dependent: contextualized embeddings yield higher feature-specific selectivity and different layer-wise profiles than isolated embeddings. Across models and methods, final-layer representations are rarely optimal for recovering psycholinguistic information with linear probes. Despite these differences, models exhibit a shared depth ordering of meaning dimensions, with lexical properties peaking earlier and experiential and affective dimensions peaking later. Together, these results show that where meaning "lives" in transformer models reflects an interaction between methodological choices and architectural constraints.

---

### An Algorithmic Framework for Systematic Literature Reviews: A Case Study for Financial Narratives

Authors: Gabin Taibi, Joerg Osterrieder
Published: 2026-01-07
Categories: q-fin.GN, cs.AI
arXiv: https://arxiv.org/abs/2601.03794v1

This paper introduces an algorithmic framework for conducting systematic literature reviews (SLRs), designed to improve efficiency, reproducibility, and selection quality assessment in the literature review process. The proposed method integrates Natural Language Processing (NLP) techniques, clustering algorithms, and interpretability tools to automate and structure the selection and analysis of academic publications. The framework is applied to a case study focused on financial narratives, an emerging area in financial economics that examines how structured accounts of economic events, formed by the convergence of individual interpretations, influence market dynamics and asset prices. Drawing from the Scopus database of peer-reviewed literature, the review highlights research efforts to model financial narratives using various NLP techniques. Results reveal that while advances have been made, the conceptualization of financial narratives remains fragmented, often reduced to sentiment analysis, topic modeling, or their combination, without a unified theoretical framework. The findings underscore the value of more rigorous and dynamic narrative modeling approaches and demonstrate the effectiveness of the proposed algorithmic SLR methodology.

---